Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claws are now a new layer on top of LLM agents

twitter.com

Post reply on HN
Print view View original

351–360 of 1001 posts

Re: Claws are now a new layer on top of LLM agents

#351

Post by ttul »

logicprog wrote: post #282
leprechaun1066 wrote: post #215

Earlier quoted context omitted.

> just like LLM agents were a new layer on top of LLMs, Claws are now a new layer on top of LLM agents, taking the orchestration, scheduling, context, tool calls and a kind of persistence to a next level. Layers of "I have no idea what the machine is doing" on top of other layers of "I have no idea what the machine is doing". This will end well...

Yeah, in the interest of full disclosure, while Claws seem like a fun toy to me, I tried ZeroClaw out and it was... kind of awful. There's no ability to see what tools agents are running, and what the results of those tools are, or cancel actions, or anything, and tools fail often enough (if you're trying to mind security to at least some degree) that the things just hallucinate wildly and don't do anything useful.

The ZeroClaw team is focusing their efforts on correctness and security by design. Observability is not yet there but the project is moving very rapidly. Their approach, I believe, is right for the long term.

Re: Claws are now a new layer on top of LLM agents

#352

Post by lifty »

lmf4lol wrote: post #299
idontwantthis wrote: post #270

Earlier quoted context omitted.

What have you done with it?

a lot of really fun stuff. From fun little scripts to more complex business/life/hibby admin stuff that annoyed me a lot (eg organizing my research). for instance i can just drop it a YT link in Telegram, and it then will automatically download the transcripts, scan them, and match them to my research notes. If it detects overlap it will suggest a link in the knowledge base. Works super nice for me because i am a cha…

What model do you use it with? And through which API, openrouter? Wondering how you manage cost because it can get quite expensive

Re: Claws are now a new layer on top of LLM agents

#354

Post by chasd00 »

deepsquirrelnet wrote: post #277
claytonaalves wrote: post #219

I'm impressed with how we moved from "AI is dangerous", "Skynet", "don't give AI internet access or we are doomed", "don't let AI escape" to "Hey AI, here is internet, do whatever you want".

The DoDs recent beef with Anthropic over their right to restrict how Claude can be used is revealing. > Though Anthropic has maintained that it does not and will not allow its AI systems to be directly used in lethal autonomous weapons or for domestic surveillance Autonomous AI weapons is one of the things the DoD appears to be pursuing. So bring back the Skynet people, because that’s where we apparently are. 1. http…

hasn't Ukraine already proved out autonomous weapons on the battlefield? There was a NYT podcast a couple years ago where the interviewed higher up in the Ukraine military and they said it's already in place with fpv drones, loitering, target identification, attack, the whole 9 yards.

You don't need an LLM to do autonomous weapons, a modern Tomahawk cruise missile is pretty autonomous. The only change to a modern tomahawk would be adding parameters of what the target looks like and tasking the missile with identifying a target. The missile pretty much does everything else already ( flying, routing, etc ).

Re: Claws are now a new layer on top of LLM agents

#355

Post by efromvt »

embedding-shape wrote: post #181
arcwhite wrote: post #151

Earlier quoted context omitted.

Once a conversation with a user is established, telegram bots can bleep away at you. Mine pings me whenever it puts a PR up, and when it's done responding to code reviews etc.

Right, but again that's not actually outbound at all, what you're describing is only inbound. Again, I thought the whole point was that the agent could start acting autonomously to some degree, not allow outbound kind of defeats the entire purpose, doesn't it?

There's a lot of useful autonomous things that don't require unrestricted outbound communication, but agreed that the "safe" claw configuration probably falls quite a bit short of the popular perception of a full AI assistant at this point.

Re: Claws are now a new layer on top of LLM agents

#356

Post by GTP »

zozbot234 wrote: post #291
GTP wrote: post #289

I'm genuinely wondering if this sort of AI revolution (or bubble, depending on which side you're in) is worth it. Yes, there are some cool use cases. But, you have to balance those with increased GPU, RAM and storage prices, and OSS projects struggling to keep up with people opening pull requests or vulnerability disclosures that turn out to be AI slop. Which lead GitHub to introduce the possibility to disable pull r…

The increased hardware prices are temporary and will only spur further expansion and innovation throughout the industry, so they're actually very good news. And the compute used for a single LLM request is quite negligible even for the largest models and the highest-effort tasks, never mind routine requests; just look at how little AI inference costs when it's sold by third parties (not proprietary model makers) at s…

Problem is, even though a single LLM call is negligible, their aggregate is not. We ended up invoking an LLM for each web search, and there are people using them for tasks that could be trivially carried out by much less energy-hungry tools. Yes, using an LLM can be much more convinient than learning how to use 10 different tools, but this is killing a mosquito with a bazooka.

> We don't need complete automation of every complex task, AI can still be very helpful even if doesn't quite make that bar.

This is very true, but the direction we took now is to stuff AI everywhere. If this turns out to be a bubble, it will eventually pop and we will be back to a more balanced use of AI, but the only sign I saw of this maybe happening is Microsoft's evaluation dropping, allegedly due to their insistence at putting AI into Windows 11.

Regarding the HW prices being only a temporary increase, I'm not sure about it: I heard some manufacturers already have agreements that will make them sell most of their production to cloud providers for the next two-three years.

Re: Claws are now a new layer on top of LLM agents

#357

Post by andsoitis »

xrd wrote: post #296
sph wrote: post #263

Earlier quoted context omitted.

This is exactly why artificial super-intelligences are scary. Not necessarily because of its potential actions, but because humans are stupid, and would readily sell their souls and release it into the wild just for an ounce of greed or popularity. And people who don't see it as an existential problem either don't know how deep human stupidity can run, or are exactly those that would greedily seek a quick profit befo…

I love this. Another way of saying it: the problem we should be focused on is not how smart the AI is getting. The problem we should be focused on is how dumb people are getting (or have been for all of eternity) and how they will facilitate and block their own chance of survival. That seems uniquely human but I'm not a ethnobiologist. A corollary to that is that the only real chance for survival is that a plurality…

> The problem we should be focused on is how dumb people are getting (or have been for all of eternity)

Over the arc of time, I’m not sure that an accurate characterization is that humans have been getting dumber and dumber. If that were true, we must have been super geniuses 3000 years ago!

I think what is true is that the human condition and age old questions are still with us and we’re still on the path to trying to figure out ourselves and the cosmos.

Re: Claws are now a new layer on top of LLM agents

#358

Post by chasd00 »

zer00eyz wrote: post #303
deepsquirrelnet wrote: post #277

Earlier quoted context omitted.

The DoDs recent beef with Anthropic over their right to restrict how Claude can be used is revealing. > Though Anthropic has maintained that it does not and will not allow its AI systems to be directly used in lethal autonomous weapons or for domestic surveillance Autonomous AI weapons is one of the things the DoD appears to be pursuing. So bring back the Skynet people, because that’s where we apparently are. 1. http…

> Autonomous AI weapons In theory, you can do this today, in your garage. Buy a quad as a kit. (cheap) Figure out how to arm it (the trivial part). Grab yolo, tuned for people detection. Grab any of the off the shelf facial recognition libraries. You can mostly run this on phone hardware, and if you're stripping out the radios then possibly for days. The shim you have to write: software to fly the drone into the pers…

> software to fly the drone into the person... and thats probably around somewhere out there as well.

ardupilot + waypoint nav would do it for fixed locations. The camera identifies a target, gets the gps cooridnates and sets a waypoint. I would be shocked if there wasn't extensions available (maybe not officially) for flying to a "moving location". I'm in the high power rocketry hobby and the knowledge to add control surfaces and processing to autonomously fly a rocket to a location is plenty available. No one does it because it's a bad look for a hobby that already raises eyebrows.

Re: Claws are now a new layer on top of LLM agents

#360

Post by BeetleB »

krelian wrote: post #127
dlt713705 wrote: post #61

Earlier quoted context omitted.

In a VM or a separate host with access to specific credentials in a very limited purpose. In any case, the data that will be provided to the agent must be considered compromised and/or having been leaked. My 2 cents.

Maybe I'm missing something obvious but, being contained and only having access to specific credentials is all nice and well but there is still an agent that orchestrates between the containers that has access to everything with one level of indirection.

I don't see why you think there is. Put Openclaw on a locked down VM. Don't put anything you're not willing to lose on that VM.
Post reply on HN